Examples with CorruptIndexException org.apache.lucene.index.CorruptIndexException used on opensource projects

Example 31 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class Lucene50LiveDocsFormat method readLiveDocs.

@Override
public Bits readLiveDocs(Directory dir, SegmentCommitInfo info, IOContext context) throws IOException {
    long gen = info.getDelGen();
    String name = IndexFileNames.fileNameFromGeneration(info.info.name, EXTENSION, gen);
    final int length = info.info.maxDoc();
    try (ChecksumIndexInput input = dir.openChecksumInput(name, context)) {
        Throwable priorE = null;
        try {
            CodecUtil.checkIndexHeader(input, CODEC_NAME, VERSION_START, VERSION_CURRENT, info.info.getId(), Long.toString(gen, Character.MAX_RADIX));
            long[] data = new long[FixedBitSet.bits2words(length)];
            for (int i = 0; i < data.length; i++) {
                data[i] = input.readLong();
            }
            FixedBitSet fbs = new FixedBitSet(data, length);
            if (fbs.length() - fbs.cardinality() != info.getDelCount()) {
                throw new CorruptIndexException("bits.deleted=" + (fbs.length() - fbs.cardinality()) + " info.delcount=" + info.getDelCount(), input);
            }
            return fbs;
        } catch (Throwable exception) {
            priorE = exception;
        } finally {
            CodecUtil.checkFooter(input, priorE);
        }
    }
    throw new AssertionError();
}

Example 32 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class Lucene50SegmentInfoFormat method read.

@Override
public SegmentInfo read(Directory dir, String segment, byte[] segmentID, IOContext context) throws IOException {
    final String fileName = IndexFileNames.segmentFileName(segment, "", Lucene50SegmentInfoFormat.SI_EXTENSION);
    try (ChecksumIndexInput input = dir.openChecksumInput(fileName, context)) {
        Throwable priorE = null;
        SegmentInfo si = null;
        try {
            CodecUtil.checkIndexHeader(input, Lucene50SegmentInfoFormat.CODEC_NAME, Lucene50SegmentInfoFormat.VERSION_START, Lucene50SegmentInfoFormat.VERSION_CURRENT, segmentID, "");
            final Version version = Version.fromBits(input.readInt(), input.readInt(), input.readInt());
            final int docCount = input.readInt();
            if (docCount < 0) {
                throw new CorruptIndexException("invalid docCount: " + docCount, input);
            }
            final boolean isCompoundFile = input.readByte() == SegmentInfo.YES;
            final Map<String, String> diagnostics = input.readMapOfStrings();
            final Set<String> files = input.readSetOfStrings();
            final Map<String, String> attributes = input.readMapOfStrings();
            si = new SegmentInfo(dir, version, null, segment, docCount, isCompoundFile, null, diagnostics, segmentID, attributes, null);
            si.setFiles(files);
        } catch (Throwable exception) {
            priorE = exception;
        } finally {
            CodecUtil.checkFooter(input, priorE);
        }
        return si;
    }
}

Example 33 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class CodecUtil method checksumEntireFile.

/** 
   * Clones the provided input, reads all bytes from the file, and calls {@link #checkFooter} 
   * <p>
   * Note that this method may be slow, as it must process the entire file.
   * If you just need to extract the checksum value, call {@link #retrieveChecksum}.
   */
public static long checksumEntireFile(IndexInput input) throws IOException {
    IndexInput clone = input.clone();
    clone.seek(0);
    ChecksumIndexInput in = new BufferedChecksumIndexInput(clone);
    assert in.getFilePointer() == 0;
    if (in.length() < footerLength()) {
        throw new CorruptIndexException("misplaced codec footer (file truncated?): length=" + in.length() + " but footerLength==" + footerLength(), input);
    }
    in.seek(in.length() - footerLength());
    return checkFooter(in);
}

Example 34 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class CodecUtil method checkFooter.

/** 
   * Validates the codec footer previously written by {@link #writeFooter}, optionally
   * passing an unexpected exception that has already occurred.
   * <p>
   * When a {@code priorException} is provided, this method will add a suppressed exception 
   * indicating whether the checksum for the stream passes, fails, or cannot be computed, and 
   * rethrow it. Otherwise it behaves the same as {@link #checkFooter(ChecksumIndexInput)}.
   * <p>
   * Example usage:
   * <pre class="prettyprint">
   * try (ChecksumIndexInput input = ...) {
   *   Throwable priorE = null;
   *   try {
   *     // ... read a bunch of stuff ... 
   *   } catch (Throwable exception) {
   *     priorE = exception;
   *   } finally {
   *     CodecUtil.checkFooter(input, priorE);
   *   }
   * }
   * </pre>
   */
public static void checkFooter(ChecksumIndexInput in, Throwable priorException) throws IOException {
    if (priorException == null) {
        checkFooter(in);
    } else {
        try {
            long remaining = in.length() - in.getFilePointer();
            if (remaining < footerLength()) {
                // corruption caused us to read into the checksum footer already: we can't proceed
                priorException.addSuppressed(new CorruptIndexException("checksum status indeterminate: remaining=" + remaining + ", please run checkindex for more details", in));
            } else {
                // otherwise, skip any unread bytes.
                in.skipBytes(remaining - footerLength());
                // now check the footer
                try {
                    long checksum = checkFooter(in);
                    priorException.addSuppressed(new CorruptIndexException("checksum passed (" + Long.toHexString(checksum) + "). possibly transient resource issue, or a Lucene or JVM bug", in));
                } catch (CorruptIndexException t) {
                    priorException.addSuppressed(t);
                }
            }
        } catch (Throwable t) {
            // catch-all for things that shouldn't go wrong (e.g. OOM during readInt) but could...
            priorException.addSuppressed(new CorruptIndexException("checksum status indeterminate: unexpected exception", in, t));
        }
        throw IOUtils.rethrowAlways(priorException);
    }
}

Example 35 with CorruptIndexException

use of org.apache.lucene.index.CorruptIndexException in project lucene-solr by apache.

the class CodecUtil method validateFooter.

private static void validateFooter(IndexInput in) throws IOException {
    long remaining = in.length() - in.getFilePointer();
    long expected = footerLength();
    if (remaining < expected) {
        throw new CorruptIndexException("misplaced codec footer (file truncated?): remaining=" + remaining + ", expected=" + expected + ", fp=" + in.getFilePointer(), in);
    } else if (remaining > expected) {
        throw new CorruptIndexException("misplaced codec footer (file extended?): remaining=" + remaining + ", expected=" + expected + ", fp=" + in.getFilePointer(), in);
    }
    final int magic = in.readInt();
    if (magic != FOOTER_MAGIC) {
        throw new CorruptIndexException("codec footer mismatch (file truncated?): actual footer=" + magic + " vs expected footer=" + FOOTER_MAGIC, in);
    }
    final int algorithmID = in.readInt();
    if (algorithmID != 0) {
        throw new CorruptIndexException("codec footer mismatch: unknown algorithmID: " + algorithmID, in);
    }
}